[petsc-dev] PetscHashIJ scaling problem?
Matthew Knepley
knepley at gmail.com
Mon Nov 11 16:12:26 CST 2013
On Mon, Nov 11, 2013 at 4:02 PM, Jed Brown <jedbrown at mcs.anl.gov> wrote:
> Matthew Knepley <knepley at gmail.com> writes:
> > I rewrote insertion for DMLabel to use the hash table, and convert to
> flat
> > arrays after insertion. Now its all linear:
>
> Nice. Did you check how many hash operations per second this works out
> to? Is this still the leading setup cost?
>
I did not check, but it would be interesting to check 3D since that it 4
part keys. It by far
the leading cost in mesh setup, but matrix preallocation is 3x more
expensive right now.
Matt
--
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20131111/364d1492/attachment.html>
More information about the petsc-dev
mailing list